370 likes | 503 Views
Project Eyeris, May 13-20. TEAM Will Bryan Tyler Burnham Scott Connell Justin Derby Kris Scott Arjay Vander Velden ADVISOR Daji Qiao CLIENT Stephen Gilbert,VRAC. Client. Virtual Reality Applications Center (VRAC). Problem Statement. No mobile solution tracks both eyes
E N D
Project Eyeris, May 13-20 TEAM Will Bryan Tyler Burnham Scott Connell Justin Derby Kris Scott Arjay Vander Velden ADVISOR Daji Qiao CLIENT Stephen Gilbert,VRAC
Client • Virtual Reality Applications Center (VRAC)
Problem Statement • No mobile solution tracks both eyes • Need for real-time streaming • Need solution to allow for viewers to analyze the data as the study is happening
Concept Sketch • Embedded, real-time eye tracking system • Stream outward video and eye tracking data wirelessly • Will be used in the C6/MIRAGE for virtual reality applications
Functional Requirements • Track both eyes for 3D depth • Two-hour, onboard cache of world view video and eye data • Real-time, wireless transmission of world view video • Real-time, wireless transmission of eye tracking data • Video and eye tracking data must be in-sync
Non-Functional Requirements General Requirements • Glasses will be active, stereoscopic glasses • System must be unobstructive and nonintrusive • Battery must last at least three hours
Non-Functional Requirements Video Requirements • World-view camera must be high definition (720p or 1080p) • The sensor camera must be 640x480 at 30fps
Non-Functional Requirements Physical Requirements • Weight constraints: Glasses – 2.3 lbs.; Backpack – 5 lbs. • Dimensional constraints: Glasses – no wider than 10 inches
Existing Market Tobii ($45,000) • No hardware adjustments necessary • System guided calibration • Lightweight & discrete • Parallax compensation • Millisecond data sync
Existing Market SMI ($30,000) • Real time & recording • Audio
Project Justification What can we improve upon? • High resolution real-time streaming over Wi-Fi • 3D vector tracking (adds depth to tracking location) • Cost of the system
Resource and Cost Estimate • Resources • 2 Gumstix Boards • 1 PandaBoard • 4 Inward-Facing Cameras • 1 Outward-Facing Camera • 1 Battery Pack • PCB • Wires • Stereo Glasses • Cost Estimate: Approx. ~$1,000
Project Milestones End of Fall semester: • Finished Design Document • Finished Project Plan • Working 2D Eye-Tracking algorithm End of Winter break: • ~50% of the modules implemented • All hardware ordered End of Spring semester: • Fully working product
Functional Decomposition Glasses
Functional Decomposition Mainboard
Functional Decomposition Network
Hardware Used • Gumstix Duo Vero • PandaBoard ES • Battery (TBD) • CMOS Cameras • Web Camera
Software Used • OpenCV • TBB (Threading Building Blocks) • Boost (C++) • Java Runtime
Platforms Used • Linux • Windows
Test Plan • Unit testing • Real-world Testing • Eye testing • Wireless testing • Blackbox testing • Whitebox testing
Metrics • Network throughput • Capture rate of cameras • Accuracy of eye tracking • Accuracy of depth
Project Status • First portion of eye tracking done • Almost all hardware in • Remaining hardware has been ordered • Wrote scripts to compile software needed for the eye-tracking algorithm • Can run programs on the Gumstix
Task Responsibility • Justin Derby (SE) • Software development • Eye tracking • Tyler Burnham (SE) • Software development • Eye tracking • Arjay Vander Velden (CPR E) • Middle layer software development • Scott Connell (CPR E) • Middle layer software development • Will Bryan (CPR E) • Embedded Programming / Interfaces • Kris Scott (EE) • Physical hardware
Plan for Next Semester • Implementing • Prototyping • Testing • Bug Fixing • Testing again • More bug fixing • Finished product